feat(paddleocr-vl): add PaddleOCR-VL GPU Dockerfile, pin vllm, update CPU image deps, and improve entrypoint and tests

Dockerfile_paddleocr_vl

@@ -39,11 +39,9 @@ RUN pip install --no-cache-dir --upgrade pip && \
     torchvision \
     --index-url https://download.pytorch.org/whl/cu124
 
-# Install vLLM (nightly for PaddleOCR-VL support)
+# Install vLLM 0.11.1 (first stable release with PaddleOCR-VL support)
 RUN pip install --no-cache-dir \
-    vllm \
-    --pre \
-    --extra-index-url https://wheels.vllm.ai/nightly \
+    vllm==0.11.1 \
     --extra-index-url https://download.pytorch.org/whl/cu124
 
 # Install additional dependencies